© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254052
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     natthi
    0.44
     traje
    0.39
     어렵
    0.39
    難しい
    0.38
     thatched
    0.38
     toe
    0.37
     süt
    0.36
    ("["
    0.36
     calling
    0.35
     kol
    0.35
    POSITIVE LOGITS
    xFFFF
    0.46
     ILO
    0.45
    Globals
    0.42
    Pre
    0.42
    Ill
    0.41
     Pre
    0.40
    ILLE
    0.39
    IDO
    0.39
    ILS
    0.38
    ILITY
    0.38
    Activations Density 0.000%

    No Known Activations